# Uncovering predictability in the evolution of the WTI oil futures curve

## TL;DR

This paper introduces a functional time series method for modeling and forecasting WTI oil futures, demonstrating its advantages over traditional approaches through empirical evaluation and out-of-sample testing.

## Contribution

It proposes a novel functional time series approach that better captures the dynamics of oil futures prices compared to classical discrete models.

## Key findings

- The method outperforms benchmarks in finite-sample tests.
- It consistently ranks in the superior set during out-of-sample evaluations.
- The approach effectively exploits underlying process dynamics.

## Abstract

Accurately forecasting the price of oil, the world's most actively traded commodity, is of great importance to both academics and practitioners. We contribute by proposing a functional time series based method to model and forecast oil futures. Our approach boasts a number of theoretical and practical advantages including effectively exploiting underlying process dynamics missed by classical discrete approaches. We evaluate the finite-sample performance against established benchmarks using a model confidence set test. A realistic out-of-sample exercise provides strong support for the adoption of our approach with it residing in the superior set of models in all considered instances.